Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens (digits and decimal points), effectively spotting numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anners
    -0.07
     platinum
    -0.06
     appellant
    -0.06
    (timer
    -0.06
     USPS
    -0.06
    Claims
    -0.06
    uncios
    -0.06
    -current
    -0.06
    *sizeof
    -0.06
    oward
    -0.06
    POSITIVE LOGITS
    생활
    0.07
     اتفاق
    0.07
     å
    0.06
     у
    0.06
    	Iterator
    0.06
    .isSuccess
    0.06
     konce
    0.06
     نمایش
    0.06
    :animated
    0.06
    Subview
    0.06
    Act Density 0.090%

    No Known Activations